{"total":178,"rows":[{"id":"2410.10934","title":"Agent-as-a-Judge: Evaluate Agents with Agents","created":"2024-10-14","cited_by_count":238,"area":"agents"},{"id":"2411.18279","title":"Large Language Model-Brained GUI Agents: A Survey","created":"2024-11-27","cited_by_count":162,"area":"agents"},{"id":"2507.13334","title":"A Survey of Context Engineering for Large Language Models","created":"2025-07-17","cited_by_count":126,"area":null},{"id":"2502.14847","title":"Red-Teaming LLM Multi-Agent Systems via Communication Attacks","created":"2025-02-20","cited_by_count":122,"area":"agents"},{"id":"2508.03680","title":"Agent Lightning: Train ANY AI Agents with Reinforcement Learning","created":"2025-08-05","cited_by_count":109,"area":"lr"},{"id":"2511.13646","title":"Live-SWE-agent: Can Software Engineering Agents Self-Evolve on the Fly?","created":"2025-11-17","cited_by_count":95,"area":"agents"},{"id":"2412.03563","title":"From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agents","created":"2024-12-04","cited_by_count":82,"area":"agents"},{"id":"2506.11791","title":"SEC-bench: Automated Benchmarking of LLM Agents on Real-World Software Security Tasks","created":"2025-06-13","cited_by_count":75,"area":"agents"},{"id":"2507.02554","title":"AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench","created":"2025-07-03","cited_by_count":71,"area":"agents"},{"id":"2410.24198","title":"SelfCodeAlign: Self-Alignment for Code Generation","created":"2024-10-31","cited_by_count":62,"area":null},{"id":"2411.00622","title":"Lingma SWE-GPT: An Open Development-Process-Centric Language Model for Automated Software Improvement","created":"2024-11-01","cited_by_count":61,"area":"agents"},{"id":"2409.16165","title":"EnIGMA: Interactive Tools Substantially Assist LM Agents in Finding Security Vulnerabilities","created":"2024-09-24","cited_by_count":52,"area":"agents"},{"id":"2509.23586","title":"Reducing Cost of LLM Agents with Trajectory Reduction","created":"2025-09-28","cited_by_count":48,"area":"agents"},{"id":"2503.12434","title":"A Survey on the Optimization of Large Language Model-based Agents","created":"2025-03-16","cited_by_count":46,"area":"agents"},{"id":"2601.16746","title":"SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents","created":"2026-01-23","cited_by_count":44,"area":"agents"},{"id":"2411.12924","title":"Human-In-the-Loop Software Development Agents","created":"2024-11-19","cited_by_count":42,"area":"agents"},{"id":"2503.14443","title":"EnvBench: A Benchmark for Automated Environment Setup","created":"2025-03-18","cited_by_count":36,"area":null},{"id":"2506.00618","title":"RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents","created":"2025-05-31","cited_by_count":35,"area":"mllm"},{"id":"2509.09734","title":"MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated Tools","created":"2025-09-10","cited_by_count":32,"area":"agents"},{"id":"2602.07274","title":"TermiGen: High-Fidelity Environment and Robust Trajectory Synthesis for Terminal Agents","created":"2026-02-06","cited_by_count":29,"area":"agents"},{"id":"2508.11126","title":"AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunities","created":"2025-08-15","cited_by_count":28,"area":"agents"},{"id":"2506.08379","title":"Reinforce LLM Reasoning through Multi-Agent Reflection","created":"2025-06-10","cited_by_count":27,"area":"lr"},{"id":"2410.14209","title":"Agents4PLC: Automating Closed-loop PLC Code Generation and Verification in Industrial Control Systems using LLM-based Agents","created":"2024-10-18","cited_by_count":26,"area":"agents"},{"id":"2511.04427","title":"Speed at the Cost of Quality: How Cursor AI Increases Short-Term Velocity and Long-Term Complexity in Open-Source Projects","created":"2025-11-06","cited_by_count":24,"area":"agents"},{"id":"2508.02744","title":"Large Language Model-based Data Science Agent: A Survey","created":"2025-08-02","cited_by_count":23,"area":"agents"},{"id":"2602.10999","title":"CLI-Gym: Scalable CLI Task Generation via Agentic Environment Inversion","created":"2026-02-11","cited_by_count":23,"area":"agents"},{"id":"2503.22424","title":"Issue Localization via LLM-Driven Iterative Code Graph Searching","created":"2025-03-28","cited_by_count":22,"area":null},{"id":"2504.14757","title":"SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugs","created":"2025-04-20","cited_by_count":22,"area":null},{"id":"2509.10147","title":"Virtual Agent Economies","created":"2025-09-12","cited_by_count":21,"area":null},{"id":"2508.13143","title":"Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks","created":"2025-08-18","cited_by_count":20,"area":"agents"},{"id":"2504.21751","title":"CodeFlowBench: A Multi-turn, Iterative Benchmark for Complex Code Generation","created":"2025-04-30","cited_by_count":17,"area":null},{"id":"2412.14234","title":"Syzygy: Dual Code-Test C to (safe) Rust Translation using LLMs and Dynamic Analysis","created":"2024-12-18","cited_by_count":16,"area":null},{"id":"2412.18371","title":"Defining and Detecting the Defects of the Large Language Model-based Autonomous Agents","created":"2024-12-24","cited_by_count":16,"area":"agents"},{"id":"2503.23145","title":"CodeARC: Benchmarking Reasoning Capabilities of LLM Agents for Inductive Program Synthesis","created":"2025-03-29","cited_by_count":16,"area":"lr"},{"id":"2604.09297","title":"SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering","created":"2026-04-10","cited_by_count":15,"area":"agents"},{"id":"2605.03378","title":"ARGUS: Defending LLM Agents Against Context-Aware Prompt Injection","created":"2026-05-05","cited_by_count":14,"area":"agents"},{"id":"2509.18362","title":"FastMTP: Accelerating LLM Inference with Enhanced Multi-Token Prediction","created":"2025-09-16","cited_by_count":13,"area":"inference"},{"id":"2512.15834","title":"Optimizing Agentic Language Model Inference via Speculative Tool Calls","created":"2025-12-17","cited_by_count":13,"area":"agents"},{"id":"2506.16136","title":"Seeing is Fixing: Cross-Modal Reasoning with Multimodal LLMs for Visual Software Issue Fixing","created":"2025-06-19","cited_by_count":12,"area":"lr"},{"id":"2601.22129","title":"SWE-Replay: Efficient Test-Time Scaling for Software Engineering Agents","created":"2026-01-29","cited_by_count":12,"area":"lr"},{"id":"2412.14764","title":"CodeRepoQA: A Large-scale Benchmark for Software Engineering Question Answering","created":"2024-12-19","cited_by_count":11,"area":null},{"id":"2604.02547","title":"Beyond Resolution Rates: Behavioral Drivers of Coding Agent Success and Failure","created":"2026-04-02","cited_by_count":11,"area":"lr"},{"id":"2605.26563","title":"TrajAudit: Automated Failure Diagnosis for Agentic Coding Systems","created":"2026-05-26","cited_by_count":11,"area":"agents"},{"id":"2411.13941","title":"LLMs as Continuous Learners: Improving the Reproduction of Defective Code in Software Issues","created":"2024-11-21","cited_by_count":10,"area":null},{"id":"2412.17146","title":"LLM Agent for Fire Dynamics Simulations","created":"2024-12-22","cited_by_count":10,"area":"agents"},{"id":"2505.20749","title":"Can Agents Fix Agent Issues?","created":"2025-05-27","cited_by_count":9,"area":"agents"},{"id":"2506.07524","title":"TAI3: Testing Agent Integrity in Interpreting User Intent","created":"2025-06-09","cited_by_count":9,"area":"agents"},{"id":"2506.09420","title":"A Call for Collaborative Intelligence: Why Human-Agent Systems Should Precede AI Autonomy","created":"2025-06-11","cited_by_count":9,"area":"agents"},{"id":"2509.00616","title":"TimeCopilot","created":"2025-08-30","cited_by_count":9,"area":"agents"},{"id":"2410.08806","title":"Don't Transform the Code, Code the Transforms: Towards Precise Code Rewriting using LLMs","created":"2024-10-11","cited_by_count":8,"area":null},{"id":"2505.12594","title":"AD-AGENT: A Multi-agent Framework for End-to-end Anomaly Detection","created":"2025-05-19","cited_by_count":8,"area":"agents"},{"id":"2512.22154","title":"Practical challenges of control monitoring in frontier AI deployments","created":"2025-12-15","cited_by_count":8,"area":null},{"id":"2607.12747","title":"Tracing Agentic Failure from the Flow of Success","created":"2026-07-14","cited_by_count":8,"area":"agents"},{"id":"2409.19894","title":"TransAgent: Enhancing LLM-Based Code Translation via Fine-Grained Execution Alignment","created":"2024-09-30","cited_by_count":7,"area":null},{"id":"2508.01443","title":"Tuning LLM-based Code Optimization via Meta-Prompting: An Industrial Perspective","created":"2025-08-02","cited_by_count":7,"area":null},{"id":"2511.00872","title":"A Comprehensive Empirical Evaluation of Agent Frameworks on Code-centric Software Engineering Tasks","created":"2025-11-02","cited_by_count":7,"area":"agents"},{"id":"2601.05777","title":"EET: Experience-Driven Early Termination for Cost-Efficient Software Engineering Agents","created":"2026-01-09","cited_by_count":7,"area":"agents"},{"id":"2605.12913","title":"Revisiting DAgger in the Era of LLM-Agents","created":"2026-05-13","cited_by_count":7,"area":"agents"},{"id":"2501.11086","title":"Evaluating LLM-Based Regression Test Generation","created":"2025-01-19","cited_by_count":6,"area":null},{"id":"2504.13472","title":"CodeVisionary: An Agent-based Framework for Evaluating Large Language Models in Code Generation","created":"2025-04-18","cited_by_count":6,"area":"agents"},{"id":"2506.02546","title":"To trust or not to trust: Attention-based Trust Management for LLM Multi-Agent Systems","created":"2025-06-03","cited_by_count":6,"area":"agents"},{"id":"2509.13471","title":"An LLM Agentic Approach for Legal-Critical Software: A Case Study for Tax Prep Software","created":"2025-09-16","cited_by_count":6,"area":"agents"},{"id":"2509.24380","title":"Agentic Services Computing","created":"2025-09-29","cited_by_count":6,"area":"agents"},{"id":"2510.23761","title":"TDFlow: Agentic Workflows for Test Driven Development","created":"2025-10-27","cited_by_count":6,"area":"agents"},{"id":"2511.21572","title":"BAMAS: Structuring Budget-Aware Multi-Agent Systems","created":"2025-11-26","cited_by_count":6,"area":"agents"},{"id":"2512.22256","title":"Agentic Software Issue Resolution with Large Language Models: A Survey","created":"2025-12-24","cited_by_count":6,"area":"agents"},{"id":"2601.15232","title":"When Agents Fail: A Comprehensive Study of Bugs in LLM Agents with Automated Labeling","created":"2026-01-21","cited_by_count":6,"area":"agents"},{"id":"2607.21217","title":"ICAE-Bench: Evaluating Coding Agents as Interactive Project Builders","created":"2026-07-23","cited_by_count":6,"area":"agents"},{"id":"2609.00006","title":"Harness Engineering: Anatomy, Architecture, and Evolution of Coding Agents -- A Source-Code Study of Eleven Systems","created":"2026-07-15","cited_by_count":6,"area":"agents"},{"id":"2502.09787","title":"TableTalk: Scaffolding Spreadsheet Development with a Language Agent","created":"2025-02-13","cited_by_count":5,"area":"agents"},{"id":"2505.04670","title":"LLM Code Customization with Visual Results: A Benchmark on TikZ","created":"2025-05-07","cited_by_count":5,"area":null},{"id":"2506.09656","title":"Multi-level Value Alignment in Agentic AI Systems: Survey and Perspectives","created":"2025-06-11","cited_by_count":5,"area":"agents"},{"id":"2512.02321","title":"LeechHijack: Covert Computational Resource Exploitation in Intelligent Agent Systems","created":"2025-12-02","cited_by_count":5,"area":"agents"},{"id":"2512.11143","title":"Automated Penetration Testing with LLM Agents and Classical Planning","created":"2025-12-11","cited_by_count":5,"area":"agents"},{"id":"2604.00917","title":"Investigating Autonomous Agent Contributions in the Wild: Activity Patterns and Code Change over Time","created":"2026-04-01","cited_by_count":5,"area":"agents"},{"id":"2604.06742","title":"Evaluating LLM-Based 0-to-1 Software Generation in End-to-End CLI Tool Scenarios","created":"2026-04-08","cited_by_count":5,"area":null},{"id":"2607.03691","title":"Don't Blame the Large Language Model: How Agent Harness Evolution Shapes Coding Agent Quality","created":"2026-07-04","cited_by_count":5,"area":"agents"},{"id":"2504.20781","title":"Using LLMs in Generating Design Rationale for Software Architecture Decisions","created":"2025-04-29","cited_by_count":4,"area":null},{"id":"2508.11553","title":"SeamlessFlow: A Trainer Agent Isolation RL Framework Achieving Bubble-Free Pipelines via Tag Scheduling","created":"2025-08-15","cited_by_count":4,"area":"deeprl"},{"id":"2509.16187","title":"MatchFixAgent: Language-Agnostic Autonomous Repository-Level Code Translation Validation and Repair","created":"2025-09-19","cited_by_count":4,"area":null},{"id":"2510.10460","title":"Understanding and Bridging the Planner-Coder Gap: A Systematic Study on the Robustness of Multi-Agent Systems for Code Generation","created":"2025-10-12","cited_by_count":4,"area":"agents"},{"id":"2511.19635","title":"Agint: Agentic Graph Compilation for Software Engineering Agents","created":"2025-11-24","cited_by_count":4,"area":"agents"},{"id":"2603.05744","title":"CodeScout: Contextual Problem Statement Enhancement for Software Agents","created":"2026-03-05","cited_by_count":4,"area":"agents"},{"id":"2604.12268","title":"CodeSpecBench: Benchmarking LLMs for Executable Behavioral Specification Generation","created":"2026-04-14","cited_by_count":4,"area":null},{"id":"2604.16790","title":"Bias in the Loop: Auditing LLM-as-a-Judge for Software Engineering","created":"2026-04-18","cited_by_count":4,"area":null},{"id":"2605.25707","title":"AgentHijack: Benchmarking Computer Use Agent Robustness to Common Environment Corruptions","created":"2026-05-25","cited_by_count":4,"area":"agents"},{"id":"2411.00006","title":"Personality-Guided Code Generation Using Large Language Models","created":"2024-10-16","cited_by_count":3,"area":null},{"id":"2502.11466","title":"GiFT: Gibbs Fine-Tuning for Code Generation","created":"2025-02-17","cited_by_count":3,"area":null},{"id":"2503.22512","title":"Unlocking LLM Repair Capabilities Through Cross-Language Translation and Multi-Agent Refinement","created":"2025-03-28","cited_by_count":3,"area":"agents"},{"id":"2504.05104","title":"AI for Climate Finance: Agentic Retrieval and Multi-Step Reasoning for Early Warning System Investments","created":"2025-04-07","cited_by_count":3,"area":"lr"},{"id":"2511.08475","title":"Designing LLM-based Multi-Agent Systems for Software Engineering Tasks: Quality Attributes, Design Patterns and Rationale","created":"2025-11-11","cited_by_count":3,"area":"agents"},{"id":"2602.00592","title":"DockSmith: Scaling Reliable Coding Environments via an Agentic Docker Builder","created":"2026-01-31","cited_by_count":3,"area":"agents"},{"id":"2602.21806","title":"Where Agent Frameworks Fall Short: Examining Functional Challenges and Usability Concerns","created":"2026-02-25","cited_by_count":3,"area":"agents"},{"id":"2603.20260","title":"ProMAS: Proactive Error Forecasting for Multi-Agent Systems Using Markov Transition Dynamics","created":"2026-03-12","cited_by_count":3,"area":"agents"},{"id":"2604.16321","title":"LLM-Based Multi-Agent Systems for Code Generation: A Multi-Vocal Literature Review","created":"2026-02-25","cited_by_count":3,"area":"agents"},{"id":"2604.16335","title":"Beyond Verifiable Rewards: Rubric-Based GRM for Reinforced Fine-Tuning SWE Agents","created":"2026-03-13","cited_by_count":3,"area":"agents"},{"id":"2606.08049","title":"SKILL.nb: Selective Formalization and Gated Execution for Durable Agent Workflows","created":"2026-06-06","cited_by_count":3,"area":null},{"id":"2505.19489","title":"Taming System Complexity: Demystifying Software Engineering Agents in Diagnosing Linux Kernel Faults","created":"2025-05-26","cited_by_count":2,"area":"agents"},{"id":"2507.16395","title":"LLM-Driven Collaborative Model for Untangling Commits via Explicit and Implicit Dependency Reasoning","created":"2025-07-22","cited_by_count":2,"area":"lr"},{"id":"2508.12232","title":"LinkAnchor: An Autonomous LLM-Based Agent for Issue-to-Commit Link Recovery","created":"2025-08-17","cited_by_count":2,"area":"agents"}],"next_cursor":"100"}